{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 678,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04424778761061947,
      "grad_norm": 6.127150945779567,
      "learning_rate": 5e-06,
      "loss": 0.5902,
      "step": 10
    },
    {
      "epoch": 0.08849557522123894,
      "grad_norm": 5.74329347119261,
      "learning_rate": 5e-06,
      "loss": 0.5179,
      "step": 20
    },
    {
      "epoch": 0.13274336283185842,
      "grad_norm": 0.7209844282034923,
      "learning_rate": 5e-06,
      "loss": 0.4956,
      "step": 30
    },
    {
      "epoch": 0.17699115044247787,
      "grad_norm": 0.8838428515444021,
      "learning_rate": 5e-06,
      "loss": 0.4693,
      "step": 40
    },
    {
      "epoch": 0.22123893805309736,
      "grad_norm": 1.047241933895238,
      "learning_rate": 5e-06,
      "loss": 0.4542,
      "step": 50
    },
    {
      "epoch": 0.26548672566371684,
      "grad_norm": 0.6249873423196232,
      "learning_rate": 5e-06,
      "loss": 0.4507,
      "step": 60
    },
    {
      "epoch": 0.30973451327433627,
      "grad_norm": 0.6688340399513245,
      "learning_rate": 5e-06,
      "loss": 0.4422,
      "step": 70
    },
    {
      "epoch": 0.35398230088495575,
      "grad_norm": 0.5938577799260061,
      "learning_rate": 5e-06,
      "loss": 0.4371,
      "step": 80
    },
    {
      "epoch": 0.39823008849557523,
      "grad_norm": 0.39377946979563905,
      "learning_rate": 5e-06,
      "loss": 0.4288,
      "step": 90
    },
    {
      "epoch": 0.4424778761061947,
      "grad_norm": 0.3494222859720882,
      "learning_rate": 5e-06,
      "loss": 0.4274,
      "step": 100
    },
    {
      "epoch": 0.48672566371681414,
      "grad_norm": 0.37585161708391424,
      "learning_rate": 5e-06,
      "loss": 0.4204,
      "step": 110
    },
    {
      "epoch": 0.5309734513274337,
      "grad_norm": 0.41629482517793825,
      "learning_rate": 5e-06,
      "loss": 0.4204,
      "step": 120
    },
    {
      "epoch": 0.5752212389380531,
      "grad_norm": 0.476310089674328,
      "learning_rate": 5e-06,
      "loss": 0.4205,
      "step": 130
    },
    {
      "epoch": 0.6194690265486725,
      "grad_norm": 0.33466258836176344,
      "learning_rate": 5e-06,
      "loss": 0.4189,
      "step": 140
    },
    {
      "epoch": 0.6637168141592921,
      "grad_norm": 0.4017367648814896,
      "learning_rate": 5e-06,
      "loss": 0.4153,
      "step": 150
    },
    {
      "epoch": 0.7079646017699115,
      "grad_norm": 0.4216322560941302,
      "learning_rate": 5e-06,
      "loss": 0.4127,
      "step": 160
    },
    {
      "epoch": 0.7522123893805309,
      "grad_norm": 0.4974612613694754,
      "learning_rate": 5e-06,
      "loss": 0.4171,
      "step": 170
    },
    {
      "epoch": 0.7964601769911505,
      "grad_norm": 0.4002778638113851,
      "learning_rate": 5e-06,
      "loss": 0.4136,
      "step": 180
    },
    {
      "epoch": 0.8407079646017699,
      "grad_norm": 0.38244063424271957,
      "learning_rate": 5e-06,
      "loss": 0.4141,
      "step": 190
    },
    {
      "epoch": 0.8849557522123894,
      "grad_norm": 0.6422183389700243,
      "learning_rate": 5e-06,
      "loss": 0.4047,
      "step": 200
    },
    {
      "epoch": 0.9292035398230089,
      "grad_norm": 0.47781718318215916,
      "learning_rate": 5e-06,
      "loss": 0.4114,
      "step": 210
    },
    {
      "epoch": 0.9734513274336283,
      "grad_norm": 0.458646597184022,
      "learning_rate": 5e-06,
      "loss": 0.4066,
      "step": 220
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.40742945671081543,
      "eval_runtime": 21.8393,
      "eval_samples_per_second": 278.306,
      "eval_steps_per_second": 1.099,
      "step": 226
    },
    {
      "epoch": 1.0176991150442478,
      "grad_norm": 0.40450956449919656,
      "learning_rate": 5e-06,
      "loss": 0.3954,
      "step": 230
    },
    {
      "epoch": 1.0619469026548674,
      "grad_norm": 0.33840868352830317,
      "learning_rate": 5e-06,
      "loss": 0.3815,
      "step": 240
    },
    {
      "epoch": 1.1061946902654867,
      "grad_norm": 0.42957928697241526,
      "learning_rate": 5e-06,
      "loss": 0.376,
      "step": 250
    },
    {
      "epoch": 1.1504424778761062,
      "grad_norm": 0.44727075308000447,
      "learning_rate": 5e-06,
      "loss": 0.3824,
      "step": 260
    },
    {
      "epoch": 1.1946902654867257,
      "grad_norm": 0.3832458382206874,
      "learning_rate": 5e-06,
      "loss": 0.3799,
      "step": 270
    },
    {
      "epoch": 1.238938053097345,
      "grad_norm": 0.46565842447548633,
      "learning_rate": 5e-06,
      "loss": 0.3763,
      "step": 280
    },
    {
      "epoch": 1.2831858407079646,
      "grad_norm": 0.3663739624439434,
      "learning_rate": 5e-06,
      "loss": 0.3813,
      "step": 290
    },
    {
      "epoch": 1.3274336283185841,
      "grad_norm": 0.38686016936047624,
      "learning_rate": 5e-06,
      "loss": 0.3825,
      "step": 300
    },
    {
      "epoch": 1.3716814159292037,
      "grad_norm": 0.4469971428096629,
      "learning_rate": 5e-06,
      "loss": 0.3797,
      "step": 310
    },
    {
      "epoch": 1.415929203539823,
      "grad_norm": 0.3943929709248344,
      "learning_rate": 5e-06,
      "loss": 0.3771,
      "step": 320
    },
    {
      "epoch": 1.4601769911504425,
      "grad_norm": 0.5005987203493157,
      "learning_rate": 5e-06,
      "loss": 0.3797,
      "step": 330
    },
    {
      "epoch": 1.504424778761062,
      "grad_norm": 0.4398991459645874,
      "learning_rate": 5e-06,
      "loss": 0.3782,
      "step": 340
    },
    {
      "epoch": 1.5486725663716814,
      "grad_norm": 0.34410767390147695,
      "learning_rate": 5e-06,
      "loss": 0.3781,
      "step": 350
    },
    {
      "epoch": 1.592920353982301,
      "grad_norm": 0.3960889669303223,
      "learning_rate": 5e-06,
      "loss": 0.3749,
      "step": 360
    },
    {
      "epoch": 1.6371681415929205,
      "grad_norm": 0.4269177410578348,
      "learning_rate": 5e-06,
      "loss": 0.3774,
      "step": 370
    },
    {
      "epoch": 1.6814159292035398,
      "grad_norm": 0.5155261299248002,
      "learning_rate": 5e-06,
      "loss": 0.3804,
      "step": 380
    },
    {
      "epoch": 1.7256637168141593,
      "grad_norm": 0.43969372154192843,
      "learning_rate": 5e-06,
      "loss": 0.378,
      "step": 390
    },
    {
      "epoch": 1.7699115044247788,
      "grad_norm": 0.4476097491183775,
      "learning_rate": 5e-06,
      "loss": 0.3755,
      "step": 400
    },
    {
      "epoch": 1.8141592920353982,
      "grad_norm": 0.38686563229116155,
      "learning_rate": 5e-06,
      "loss": 0.3801,
      "step": 410
    },
    {
      "epoch": 1.8584070796460177,
      "grad_norm": 0.35475500773398083,
      "learning_rate": 5e-06,
      "loss": 0.3737,
      "step": 420
    },
    {
      "epoch": 1.9026548672566372,
      "grad_norm": 0.3300920550320411,
      "learning_rate": 5e-06,
      "loss": 0.377,
      "step": 430
    },
    {
      "epoch": 1.9469026548672566,
      "grad_norm": 0.37302140942747203,
      "learning_rate": 5e-06,
      "loss": 0.372,
      "step": 440
    },
    {
      "epoch": 1.991150442477876,
      "grad_norm": 0.3842303488060595,
      "learning_rate": 5e-06,
      "loss": 0.3734,
      "step": 450
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.39825692772865295,
      "eval_runtime": 21.4661,
      "eval_samples_per_second": 283.144,
      "eval_steps_per_second": 1.118,
      "step": 452
    },
    {
      "epoch": 2.0353982300884956,
      "grad_norm": 0.48990695812840507,
      "learning_rate": 5e-06,
      "loss": 0.3513,
      "step": 460
    },
    {
      "epoch": 2.079646017699115,
      "grad_norm": 0.45716992449403504,
      "learning_rate": 5e-06,
      "loss": 0.3424,
      "step": 470
    },
    {
      "epoch": 2.1238938053097347,
      "grad_norm": 0.4089130956180029,
      "learning_rate": 5e-06,
      "loss": 0.3436,
      "step": 480
    },
    {
      "epoch": 2.168141592920354,
      "grad_norm": 0.426162580374922,
      "learning_rate": 5e-06,
      "loss": 0.3476,
      "step": 490
    },
    {
      "epoch": 2.2123893805309733,
      "grad_norm": 0.3887768051888474,
      "learning_rate": 5e-06,
      "loss": 0.3456,
      "step": 500
    },
    {
      "epoch": 2.256637168141593,
      "grad_norm": 0.49818725927434065,
      "learning_rate": 5e-06,
      "loss": 0.346,
      "step": 510
    },
    {
      "epoch": 2.3008849557522124,
      "grad_norm": 0.3869718840156669,
      "learning_rate": 5e-06,
      "loss": 0.3458,
      "step": 520
    },
    {
      "epoch": 2.3451327433628317,
      "grad_norm": 0.4420786488564716,
      "learning_rate": 5e-06,
      "loss": 0.3409,
      "step": 530
    },
    {
      "epoch": 2.3893805309734515,
      "grad_norm": 0.4328163120927778,
      "learning_rate": 5e-06,
      "loss": 0.3487,
      "step": 540
    },
    {
      "epoch": 2.433628318584071,
      "grad_norm": 0.39197907411119853,
      "learning_rate": 5e-06,
      "loss": 0.3451,
      "step": 550
    },
    {
      "epoch": 2.47787610619469,
      "grad_norm": 0.36416856007458076,
      "learning_rate": 5e-06,
      "loss": 0.3503,
      "step": 560
    },
    {
      "epoch": 2.52212389380531,
      "grad_norm": 0.3746017341827326,
      "learning_rate": 5e-06,
      "loss": 0.3469,
      "step": 570
    },
    {
      "epoch": 2.566371681415929,
      "grad_norm": 0.3618786916476107,
      "learning_rate": 5e-06,
      "loss": 0.3464,
      "step": 580
    },
    {
      "epoch": 2.6106194690265485,
      "grad_norm": 0.41598805205539596,
      "learning_rate": 5e-06,
      "loss": 0.3435,
      "step": 590
    },
    {
      "epoch": 2.6548672566371683,
      "grad_norm": 0.37961766765714905,
      "learning_rate": 5e-06,
      "loss": 0.3486,
      "step": 600
    },
    {
      "epoch": 2.6991150442477876,
      "grad_norm": 0.39738095608916224,
      "learning_rate": 5e-06,
      "loss": 0.3488,
      "step": 610
    },
    {
      "epoch": 2.7433628318584073,
      "grad_norm": 0.40094307810609703,
      "learning_rate": 5e-06,
      "loss": 0.3459,
      "step": 620
    },
    {
      "epoch": 2.7876106194690267,
      "grad_norm": 0.355834042921306,
      "learning_rate": 5e-06,
      "loss": 0.3415,
      "step": 630
    },
    {
      "epoch": 2.831858407079646,
      "grad_norm": 0.3745969159488807,
      "learning_rate": 5e-06,
      "loss": 0.35,
      "step": 640
    },
    {
      "epoch": 2.8761061946902657,
      "grad_norm": 0.3789920652707106,
      "learning_rate": 5e-06,
      "loss": 0.3477,
      "step": 650
    },
    {
      "epoch": 2.920353982300885,
      "grad_norm": 0.3918177591119166,
      "learning_rate": 5e-06,
      "loss": 0.3477,
      "step": 660
    },
    {
      "epoch": 2.9646017699115044,
      "grad_norm": 0.33578037413287726,
      "learning_rate": 5e-06,
      "loss": 0.3466,
      "step": 670
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.3991487920284271,
      "eval_runtime": 21.5542,
      "eval_samples_per_second": 281.987,
      "eval_steps_per_second": 1.113,
      "step": 678
    },
    {
      "epoch": 3.0,
      "step": 678,
      "total_flos": 1135675252408320.0,
      "train_loss": 0.38758731908151184,
      "train_runtime": 4370.1856,
      "train_samples_per_second": 79.274,
      "train_steps_per_second": 0.155
    }
  ],
  "logging_steps": 10,
  "max_steps": 678,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1135675252408320.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}